Optimization

Understanding Gradient Clipping In Incremental Gradient Methods AISTATS 2021 Understanding Over-parameterization in Generative Adversarial Networks ICLR 2021 Understanding the Effect of Stochasticity in Policy Optimization NeurIPS 2021 Understanding the effects of data parallelism and sparsity on neural network training ICLR 2021 Understanding the role of importance weighting for deep learning ICLR 2021 Understanding the wiring evolution in differentiable neural architecture search AISTATS 2021 Unfolding-Model-Based Visualization: Theory, Method and Applications JMLR 2021 UnibucKernel: Geolocating Swiss German Jodels Using Ensemble Learning EACL 2021 Unified Interpretation of Softmax Cross-Entropy and Negative Sampling: With Case Study for Knowledge Graph Embedding ACL 2021 Unifying Width-Reduced Methods for Quasi-Self-Concordant Optimization NeurIPS 2021 Unique sparse decomposition of low rank matrices NeurIPS 2021 Universal and Flexible Optical Aberration Correction Using Deep-Prior Based Deconvolution ICCV 2021 Unsupervised Learning of Graph Hierarchical Abstractions with Differentiable Coarsening and Optimal Transport AAAI 2021 UOR at SemEval-2021 Task 12: On Crowd Annotations; Learning with Disagreements to optimise crowd truth SemEval 2021 Usable Information and Evolution of Optimal Representations During Training ICLR 2021 Using Hindsight to Anchor Past Knowledge in Continual Learning AAAI 2021 Validation Free and Replication Robust Volume-based Data Valuation NeurIPS 2021 Value-at-Risk Optimization with Gaussian Processes ICML 2021 Value-aware Approximate Attention EMNLP 2021 Variance-Aware Off-Policy Evaluation with Linear Function Approximation NeurIPS 2021 Variance Penalized On-Policy and Off-Policy Actor-Critic AAAI 2021 Variance Reduced Training with Stratified Sampling for Forecasting Models ICML 2021 Variance Reduction via Primal-Dual Accelerated Dual Averaging for Nonsmooth Convex Finite-Sums ICML 2021 Variational Data Assimilation with a Learned Inverse Observation Operator ICML 2021 Vector-output ReLU Neural Network Problems are Copositive Programs: Convex Analysis of Two Layer Networks and Polynomial-time Algorithms ICLR 2021